Meta-Learning

Ask about this topic

Overview

Meta-learning studies how experience across related tasks can prepare a model to learn a new task from a small support set, brief feedback, or context alone. Common approaches include gradient-based initialization methods such as MAML, metric and prototype methods, Bayesian methods, learned optimizers and hypernetworks, and episodic training for in-context or test-time adaptation. Applications range from few-shot vision and domain-shifted control to AutoML, scientific system identification, and language or robotic agents, where fast adaptation can reduce labeling, retraining, or optimization costs. The central challenge is transferring useful shared structure without negative transfer: task diversity, distribution shift, uncertainty, costly bilevel training, and fair evaluation of adaptation remain active concerns.

Latest papers

CardsList

166 papers20 papers in the last four weeks, level with the four weeks before. 0.1% of all new papers.

Jul 1, 2026

Learning Cardiac Motion Priors for Implicit Neural Representations

Implicit neural representations (INRs) are well suited to cardiac motion estimation, providing continuous, compact representations of motion fields. However, fitting an INR to each image sequence is time-consuming and sensitive to the optimisation trajectory. Learned priors can help guide optimisation towards plausible motion fields and enable faster adaptation, but learning priors for cardiac motion INRs remains under-explored. In this work, we compare four strategies for learning cardiac motion priors, including a population prior learned by joint optimisation, a consensus prior obtained by weight averaging, auto-decoders, and meta-learning. Using short-axis tagged cardiac magnetic resonance images from the UK Biobank, we evaluate their impact on tracking accuracy, motion behaviour, and adaptation trajectory. All learned priors substantially improved early adaptation performance compared with random initialisation. While the simple consensus prior was effective, auto-decoders recovered large deformations faster during early adaptation. Meta-learning achieved strong early performance and maintained the best adaptation trajectory over 50 iterations.

Andrew Bell, George Webber, Andrew P King +3

School of Biomedical Engineering and Imaging Sciences, King’s College London, United Kingdom · William Harvey Research Institute, Queen Mary University of London,2026 United Kingdom · Cardio-Oncology Service, Royal Brompton and Harefield Hospitals, London, United Kingdom

Implicit Neural RepresentationsMeta-LearningMedical Image AnalysisCardiac MRI
AskPDF
Jul 1, 2026

Human-Machine Collaboration on Generative Meta-Learning: Model and Algorithm

Generalizing machine learning models to environments that differ from their training distribution remains a critical hurdle, particularly when data from the target domain is entirely or partially unavailable. We propose Generative Meta-Learning with Human Feedback (GMHF), a novel framework that bridges this domain gap by leveraging expert intuition to guide data synthesis. Grounded in a theoretical analysis of generalization error, we derive bounds demonstrating that aligning the distribution of generated data with human beliefs regarding the target physics significantly mitigates risk. GMHF operationalizes this insight by employing a Conditional Neural ODE (cNODE) as a generative digital twin, coupled with a Reinforcement Learning (RL) agent. The agent iteratively refines the latent physical parameters of the generated trajectories based on feedback, effectively steering the meta-learner toward the unobserved target distribution. Empirical validation on a nonlinear Duffing oscillator shows that GMHF substantially reduces deployment loss as expert reliability increases, and that the divergence between generated and target data falls under reliable feedback, directly corroborating the divergence-minimisation mechanism predicted by our theory. Further experiments on a non-dynamical probabilistic model confirm that the framework extends beyond ODE-governed systems, establishing human-AI collaboration as a rigorous catalyst for robust generalisation under distribution shift.

Midhun Parakkal Unni, Samuel Kaski

School of Computer Science, University of Sheffield, Sheffield, UK · Centre for Machine intelligence, University of Sheffield, UK · Department of Computer Science, University of Manchester, Manchester, UK +2

Meta-LearningSynthetic Data GenerationOOD Generalization
AskPDF
Jul 1, 2026

Meta-Transfer Learning for mmWave Beam Alignment

Millimeter-wave (mmWave) beam alignment is critical for next-generation wireless systems, but existing approaches either update all parameters during adaptation or restrict updates to a subset of layers without adapting intermediate feature representations. We propose MTL-BA, a meta-transfer learning framework for multiple-input single-output (MISO) beam alignment that freezes a pre-trained convolutional backbone and meta-learns lightweight Scale-and-Shift (SS) adapters and a classifier head. Under an outdoor-to-indoor shift in DeepMIMO, MTL-BA achieves the highest Top-1 accuracy among the evaluated methods at 35 dB while updating 17×17\times fewer parameters than full fine-tuning and meta-training 6×6\times faster than MAML.

Ahmet Nuri Cevik, Sinem Coleri

Meta-LearningWireless CommunicationsCross-Domain Transfer LearningParameter-Efficient Fine-TuningMillimeter-Wave Communications
AskPDF
Jun 29, 2026

From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators

Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment. Workflows that encode recurring algorithmic patterns at the task level provide a principled framework, offering robustness across instance variations, interpretable traces for debugging, and reusability across problem instances. However, manually designing such workflows requires significant expertise and effort, limiting their broader application. While automatic workflow generation could address this bottleneck, existing methods either produce instance-specific solutions without learning task-level patterns, or cannot generalize beyond their training configurations. We present MetaFlow, which casts workflow generation as a meta-learning problem: given a task and an operator set, the model learns to compose solution strategies. MetaFlow trains in two stages: supervised fine-tuning on synthetic workflow data, followed by reinforcement learning with verifiable rewards (RLVR) that uses execution feedback across problem instances in the task to improve end-to-end success. The resulting model produces effective workflows for trained tasks and exhibits strong generalization to untrained tasks and novel operator sets. Across benchmarks in question answering, code generation, and mathematical reasoning, MetaFlow achieves performance comparable to state-of-the-art baselines on in-domain tasks with single inference, while demonstrating remarkable zero-shot generalization capabilities on out-of-domain tasks and operator sets.

Gan Luo, Zihan Qin, Bin Dong +1

School of Mathematics Science, Peking University

Zero-Shot LearningMeta-LearningLLM Post-Training
AskPDF
Jun 24, 2026

Meta-learning as a principle for human-like visual representations

The structure of human visual representations underpins our capacity for adaptive behaviour. While pretrained neural networks model human visual representations with unprecedented success, a large discrepancy remains. We propose one reason: these networks optimise a single fixed objective, whereas human representations must support open-ended tasks. We hypothesise this flexibility arises from meta-learning (learning to learn), a pressure shaping representations to acquire new tasks from few observations. To test this, we train a sequence model, without any supervision from human data, across thousands of semantically rich tasks mapping images to high-level concepts. Compared to their pretrained base encoders, meta-learned representations better predict human similarity judgements, semantic rule learning, and high-level visual cortex. Behavioural gains depend on disentangled, high-level task distributions, while brain alignment is driven primarily by the learning-to-learn pressure. Our results suggest the flexibility of human visual representations reflects the functional demand to learn new semantic relationships on the fly.

Can Demircan, Marcel Binz, Alireza Modirshanechi +1

Helmholtz Munich, Munich, Germany · Max Planck Institute for Biological Cybernetics, Tübingen, Germany

Visual Representation LearningMeta-LearningHuman Visual Perception
AskPDF
Jun 23, 2026

Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval

We develop accurate and efficient solutions for large-scale retrieval tasks where novel (zero-shot) items can arrive continuously at a rapid pace. Conventional Siamese-style approaches embed both queries and items through a small encoder and retrieve the items lying closest to the query. While this approach allows efficient addition and retrieval of novel items, the small encoder lacks sufficient capacity for the necessary world knowledge in complex retrieval tasks. The extreme classification approaches have addressed this by learning a separate classifier for each item observed in the training set which significantly increases the representation capacity of the model. Such classifiers outperform Siamese approaches on observed items, but cannot be trained for novel items due to data and latency constraints. To bridge these gaps, this paper develops: (1) A new algorithmic framework, EMMETT, which efficiently synthesizes classifiers on-the-fly for novel items, by relying on the readily available classifiers for observed items; (2) A new algorithm, IRENE, which is a simple and effective instance of EMMETT that is specifically suited for large-scale deployments, and (3) A new theoretical framework for analyzing the generalization performance in large-scale zero-shot retrieval which guides our algorithm and training related design decisions. Comprehensive experiments are conducted on a wide range of retrieval tasks which demonstrate that IRENE improves the zero-shot retrieval accuracy by up to 15% points in Recall@10 when added on top of leading encoders. Additionally, on an online A/B test in a large-scale ad retrieval task in a major search engine, IRENE improved the ad click-through rate by 4.2%. Lastly, we validate our design choices through extensive ablative experiments. The source code for IRENE is available at https://aka.ms/irene.

Sachin Yadav, Deepak Saini, Anirudh Buvanesh +6

Microsoft Research · Microsoft · Indian Institute of Technology

Zero-Shot LearningMeta-Learning
AskPDF
Jun 23, 2026

Learning Dynamical Systems from Multiple Sparse Datasets: A Hierarchical Bayesian Modeling Approach

Estimating parameters of dynamical systems from sparse, noisy, and irregularly sampled data is often severely ill-conditioned. When multiple related datasets are available, they provide additional information if the shared structure and variability are properly modeled. We propose a hierarchical Bayesian framework for probabilistic meta-learning in dynamical systems, modeling dataset-specific parameters as draws from a shared population distribution. A numerical ODE solver is embedded within gradient-based MCMC to enable efficient posterior inference of the shared population and dataset-specific parameter distribution. Experiments show improved predictive performance over unpooled methods, highlighting the potential for data-efficient system identification in settings with sparse data.

Cristian Brugnara, Lea Multerer, Marco Forgione +1

SUPSI, Dalle Molle Institute for Artificial Intelligence (IDSIA USI-SUPSI), Lugano, Switzerland

Irregular Time-Series ModelingParameter EstimationMeta-LearningBayesian InferenceNonlinear System IdentificationHierarchical Bayesian Modeling+1
AskPDF
Jun 22, 2026

Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios

Domain generalization learns from multiple source domains to generalize to unseen target domains. However, it often neglects the realistic case of label mismatch between source and target. Open set domain generalization is then proposed to recognize unseen classes in unseen domains. A simple approach trains one-vs-all classifiers to separate each class and detect outliers as unknown. Yet, the imbalance between few positive samples and many negative samples skews the decision boundary towards the positive ones, leading the model to over-reject out-of-distribution data, even from known classes in unseen domains. In this paper, we propose a novel meta-learning stategy called dualistic MEta-learning with joint DomaIn-Class matching (MEDIC), which considers implicit gradient matching towards inter-domain and inter-class task splits simultaneously to find optimal boundaries balanced for both domains and classes. Experimental results show that MEDIC not only outperforms prior methods in open set scenarios, but also maintains competitive close set generalization ability.

Xiran Wang, Jian Zhang, Lei Qi +2

State Key Laboratory for Novel Software Technology, Nanjing University, China · School of Computer Science and Engineering, Southeast University, China

Meta-LearningDomain GeneralizationOpen-Set RecognitionCross-Domain Generalization
AskPDF
Jun 14, 2026

CIWI-CKT: Chaos-Informed Wave Interference Feature Fusion and Cross-City Knowledge Transfer for Traffic Flow Forecasting

Accurate traffic flow prediction remains challenging in cross-city, data-scarce scenarios where limited historical data hinders model generalisation. The chaotic nature of traffic dynamics, complex spatio-temporal dependencies, and heterogeneous urban networks complicate few-shot learning across cities. Existing deep learning approaches either treat traffic as purely deterministic or lack mechanisms to model wave-like interference patterns essential for cross-regime traffic dynamics. To address these limitations, this paper proposes CIWI-CKT, a novel Chaos-Informed Wave Interference Feature Fusion framework with Cross-City Knowledge Transfer. Our framework introduces three core innovations: chaos-informed wave generation that extracts measurable chaos invariants and models traffic as adaptive wave components; meta-interference processing that captures wave interactions between support and query regimes while producing a predictability score for confidence estimation; and chaos-aware meta-learning that enables efficient cross-city knowledge transfer while preserving chaotic characteristics. We establish theoretical guarantees including chaos-to-wave stability, wave-induced dimension reduction, and meta-learning generalisation bounds. Extensive experiments on four real-world traffic datasets demonstrate that CIWI-CKT significantly outperforms state-of-the-art spatio-temporal graph learning, transfer learning, prompt-based, and few-shot methods, improving prediction accuracy while substantially reducing required training data.

Abdul Joseph Fofanah, Lian Wen, David Chen +1

School of Information and Communication Technology, Griffith University, Brisbane, 4111, Australia · School of Information Engineering, Chang’an University, Xi’an, China

Meta-LearningFew-Shot LearningCross-Domain Transfer LearningTraffic ForecastingChaotic Time-Series Prediction
AskPDF
Jun 8, 2026

A Guide to Estimating Conditional Average Treatment Effects in Competing Risks Settings

Conditional average treatment effects (CATEs) are central to treatment decision-making in personalized medicine. In competing risks settings, estimating CATEs from survival data allows for patient-specific assessments of treatment effectiveness for a specific event of interest while properly accounting for alternative event types. This distinction is essential in the presence of comorbidities, where competing causes of death may otherwise confound the therapeutic benefit. Focusing on right-censored survival times with binary treatment, we examine CATEs defined as covariate-conditional differences in the absolute risk for the event of interest at a fixed time. To this end, we study meta-learners which adapt machine learning algorithms for CATE estimation in competing risks scenarios. We systematically compare six meta-learners, combining Cox regression or random survival forests for risk modeling with elastic net regression or random forests for direct CATE modeling. To provide practical guidance on model selection, we evaluate their performance in multiple simulation settings, that differ in hazard complexity, treatment heterogeneity, treatment assignment, event type distribution and censoring. To facilitate applied use, we provide the R package, crsurvlearners, which implements all considered approaches.

Daniel Klippert, Sarah Friedrich, Markus Pauly

Department of Statistics, TU Dortmund University · Research Center Trustworthy Data Science and Security, University Alliance Ruhr (UA Ruhr) · Institute for Mathematics, University of Augsburg

Causal Effect EstimationMeta-LearningConditional Average Treatment Effect EstimationSurvival AnalysisIndividualized Treatment Effect Estimation
AskPDF
Jun 5, 2026

CoMetaPNS: Continually Meta-learning Personalized Neural Surrogates for Cardiac Electrophysiology Simulations

Personalized virtual heart simulations face challenges in model personalization and computational cost. While neural surrogates offer state-of-the-art solutions, they typically address either efficient personalization or training generalizable models. Recent work reframes this by learning the process of personalizing a surrogate using limited subject-specific context data, through few-shot generative modeling with set-conditioned surrogates and meta-learned amortized inference. These methods, however, assume a static and diverse training distribution with known task identifiers. When new data becomes available, they require costly retraining with all prior data to avoid catastrophic forgetting - a phenomena where the model forgets earlier tasks when trained on new ones. This is a major limitation in clinical settings where often unlabeled data arrives sequentially and full retraining is infeasible. This paper presents a new continual meta-learning framework to achieve personalized neural surrogates able to not only continually integrate information but also identify whether incoming data stems from a known or unknown dynamics source. By leveraging a continual Bayesian Gaussian Mixture Model over a memory buffer, our framework can infer the identifiers and relationships of data over time - required for effective meta-learning. Empirical results on synthetic cardiac data demonstrate superior simulation forecasting, computational scalability, and resilience to catastrophic forgetting compared to existing baselines.

Ryan Missel, Xiajun Jiang, Linwei Wang

Neural Surrogate ModelingSurrogate ModelingMeta-LearningPhysics-Based SimulationCatastrophic Forgetting
AskPDF
Jun 5, 2026

Robotic Policy Adaptation via Weight-Space Meta-Learning

Vision-Language-Action (VLA) models are emerging as a promising paradigm for robotic manipulation, enabling general-purpose policies trained from large corpora of demonstrations and action labels. However, adapting these models to new tasks still typically requires task-specific demonstrations, action annotations, and additional fine-tuning, making deployment costly and difficult to scale. We propose WIZARD, a weight-space meta-learning framework that sidesteps task-specific fine-tuning by generating task-specific LoRA parameters for a frozen VLA policy. Given only a language instruction and a short demonstration video, WIZARD predicts the corresponding adaptation weights in a single forward pass, without target-task action labels or test-time optimization. During meta-training, WIZARD learns to map task evidence directly to expert LoRA updates, capturing relationships between tasks in weight space. Experiments on LIBERO show that WIZARD improves performance by up to ~2x on unseen dataset collections and up to ~14x on unseen tasks. On a Franka Emika Panda, WIZARD consistently improves over a real-domain adapted baseline, showing that generated adapters provide task-level specialization beyond simulation.

Christian Bianchi, Siamak Yousefi, Alessio Sampieri +4

ItalAI · ItalAI and Sapeinza University of Rome

Robot Policy AdaptationRobot Skill LearningLanguage-Conditioned Robot ManipulationMeta-LearningGeneralization in Robotic ManipulationVision-Language-Action Models
AskPDF
Jun 4, 2026

Learning to Route LLMs from Implicit Cost-Performance Preferences via Meta-Learning

Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense. LLM routing aims to mitigate expenses while maintaining performance by sending queries to the most suitable model. However, existing methods cannot perform well for different user cost-performance preferences. To address this gap, we introduce a novel perceptive LLM routing paradigm for personalized and user-centric cost-performance optimization, which efficiently learns users' implicit preferences through little interaction. To handle the challenge of heterogeneous user needs, we formulate preference profiles as a set of distinct tasks in contextual bandit and propose MetaRouter, a meta-learning framework designed for preference-aware LLM routing. Experimental results show that MetaRouter outperforms strong baselines on both in-distribution and out-of-distribution tasks. Furthermore, it exhibits high efficiency in learning user preferences, robustness to changes in the routable LLMs, and scalability to multi-model routing.

Jiahao Zeng, Ming Tang, Ningning Ding

Hong Kong University of Science and Technology (Guangzhou) · Southern University of Science and Technology

Meta-LearningCost-Aware InferenceLLM Routing
AskPDF
Jun 3, 2026

R-APS: Compositional Reasoning and In-Context Meta-Learning for Constrained Design via Reflective Adversarial Pareto Search

Large language models (LLMs) are fluent on open-ended tasks, yet in agentic settings, where a system must plan, use tools, and act over extended horizons, fluency does not ensure reliable delivery. We trace this gap to three coupled structural failures: errors propagate without localization, worst-case perturbations go unevaluated, and accumulated knowledge is never invalidated. We argue these share a root cause: abductive, counterfactual, meta-inductive, corrective, and inductive reasoning pull a shared context in incompatible directions. We introduce Reflective Adversarial Pareto Search (R-APS), to our knowledge the first method addressing all three failures jointly via reasoning-mode decomposition, allocating each reasoning mode its own context and orchestrating interaction across three timescales: staged compositional reasoning with a typed validation critic (failure localization), sensitivity-guided counterfactual stress-testing as a first-class Pareto objective (robustness), and meta-inductive rule extraction with explicit invalidation (persistent memory). R-APS requires no fine-tuning and operates on a frozen LLM purely via structured protocol design. We evaluate on planar mechanism synthesis (robotics, prosthetics, mechanical design), with every candidate checked by a kinematic solver. On 32 target trajectories, R-APS delivers robustness certificates 3.5x tighter than uniform-perturbation baselines, 46% faster iterations-to-first-admission, and 2.1x Chamfer-distance reduction over Enum+GA while jointly controlling bar-count and worst-case robustness. Small 4B reasoning-specialized models prove competitive with general-purpose 70B backbones inside the protocol, suggesting structured protocols can partially offset model scale.

João Pedro Gandarela, Thiago Rios, Stefan Menzel +1

Idiap Research Institute, Switzerland · École Polytechnique Fédérale de Lausanne (EPFL), Switzerland · Honda Research Institute Europe, Germany +2

Mechanism DesignMeta-LearningCompositional ReasoningConstrained Optimization
AskPDF
Jun 1, 2026

Bayesian meta-learning for modeling Alzheimer's disease progression

Predicting whether an individual with Alzheimer's disease will experience mild or severe disease progression is essential for personalized treatment. Typically, practitioners seek to predict the distribution of a discrete disease score, conditional on an individual's current MRI volume and their historical disease trajectory. Classical statistical regression models and single-task neural networks are not well-suited for this purpose because fitting separate models is infeasible (since each individual typically has few observations), while ignoring individual-level correlation leads to poor generalization. Meta-learning, in contrast, provides a natural avenue to dynamically predict distributions without retraining and model nonlinear relationships between the outcome and covariates. Motivated by this, we propose a Bayesian meta-learner that is trained on multiple individuals but tailors the predictive disease score distribution to each individual's historical data. Our model predicts on unseen individuals without retraining, scales linearly with the number of historical observations, and is guaranteed to be less overconfident when predicting long-term disease scores compared to its deterministic counterpart. On real-world data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, our model achieves performance competitive with both single-task models and deterministic meta-learners, while substantially improving performance when predicting long-term disease progression.

Clara Hoffmann, Nadja Klein

Scientific Computing Center, Karlsruhe Institute of Technology, Germany

Alzheimer's DiseaseMeta-LearningBayesian InferenceClinical Outcome PredictionAlzheimer's Disease Progression PredictionDisease Progression Modeling
AskPDF
Jun 1, 2026

Provable Data Scaling Law for Meta Learning via Complexity Minimization

Pre-training has become a fundamental paradigm in modern machine learning, with one of its key empirical benefits being reduced downstream sample complexity as the scale of pre-training data increases. However, existing theoretical frameworks for pre-training do not fully explain this phenomenon. In this paper, we introduce complexity minimization, a novel meta-representation learning framework designed to enable theoretical analysis of this scaling behavior, which learns representations by evaluating the downstream model complexity best suited to each domain and minimizing the worst-case such complexity across source domains. Our end-to-end theoretical analysis, spanning pre-training through downstream regression, shows that this framework provably captures this scaling behavior; in particular, we show that the error rate of few-shot adaptation improves as the amount of meta-training data grows. Empirically, we demonstrate that incorporating complexity regularization into existing meta-learning methods consistently improves downstream sample efficiency.

Kazuto Fukuchi, Ryuichiro Hataya, Kota Matsui

University of Tsukuba, Japan · RIKEN AIP, Japan · SB Intuitions Corp., Japan +3

Meta-LearningFew-Shot LearningStatistical Learning TheoryData-Efficient Learning
AskPDF
May 31, 2026

UME: A Unified Meta-Generalization Framework for Cross-Domain ETA

Accurate Estimated Time of Arrival (ETA) prediction on checkout page is crucial in instant logistics for enhancing user satisfaction, optimizing dispatching, and controlling operational costs. In international on-demand delivery platforms, where ETA data originates from diverse countries or regions with different patterns, multi-domain modeling is of great importance and has been widely adopted. However, existing methods still face three critical challenges in real-world deployment. First, current multi-domain models struggle to generalize to completely unseen domains, failing to achieve zero-shot prediction during the initial cold-start phase. Second, cross-domain feature spaces are often assumed to be consistent, whereas new domains commonly suffer from structural missingness of offline (statistical) features due to the lack of historical data. Third, such feature missingness often compels industrial systems to model mature and cold-start domains separately, hindering knowledge transfer and increasing maintenance overhead. To address these challenges, we propose UME, a Unified Meta-generalization framework for ETA. Specifically, UME integrates a unified dual-branch architecture with a novel meta-learning mechanism that employs a hypernetwork-based meta learner. By leveraging domain-level knowledge and instance-level context, the meta learner empowers three meta modules to dynamically modulate feature gating, expert attention, and final prediction, capturing cross-domain correlations and facilitating intra-domain adaptation. A knowledge distillation strategy is further introduce to enhance performance. UME has now been deployed in Meituan-keeta delivery platform (the largest international food delivery platform in China). Extensive offline experiments and online A/B tests demonstrate that UME significantly outperforms existing baselines.

Duo Wang, Qiong Wu, Jianguo Wu +9

Peking University · Meituan

Event Time PredictionMeta-LearningCross-Domain Generalization
AskPDF
May 30, 2026

On the Difficulty of Learning a Meta-network for Training Data Selection

Synthetic data are increasingly used to train neural networks, yet distributional mismatch with real data limits their effectiveness when used indiscriminately. A common strategy is to learn data weights via bi-level optimization, which we refer to as Meta-learning for Training-data Selection (MTS). Interestingly, in practice, MTS often performs below expectation. We identify two obstacles in properly training MTS: a poor gradient signal-to-noise ratio (GSNR), which causes optimization difficulties, and lack of informative features that correlates with data quality. We present a mathematical analysis of MTS, which reveals the dynamics of normalized data weights and the relation between disparate data quality and poor GSNR. The analysis suggests a a simple yet effective solution: increasing the batch size. Further, we propose a set of informative features that capture the positions of training data in their distributions and training dynamics. Experiments across four benchmarks show consistent improvements, achieving average gains of 5.49% over training without selection and 2.89% over the strongest baseline.

Zilin Du, Junqi Zhao, Boyang Albert Li

College of Computing and Data Science, Nanyang Technological University, Singapore.

Meta-LearningTraining Data SelectionBilevel OptimizationNeural Network Training DynamicsSynthetic Data Selection
AskPDF
May 29, 2026

CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction

Methane is a potent greenhouse gas that significantly contributes to global warming. However, accurately estimating global methane emissions and consumption remains challenging due to the complex interactions among environmental drivers that may vary across spatial and temporal scales. Prior data-driven methods often overlook the inherent spatiotemporal heterogeneity of ecosystems, failing to explicitly capture site-specific characteristics and cross-year evolutionary dynamics. To address these issues, we propose the Contrastive Hierarchical Adaptive Meta-network (CHAM-net), a novel framework that explicitly learns from historical context to capture site-specific dynamics. CHAM-net employs a hierarchical encoder-decoder architecture, in which the encoder captures site-specific characteristics from historical data and then dynamically conditions the decoder to generate the final prediction. Experimental results demonstrate that CHAM-net consistently outperforms all baseline methods on both simulation and observational datasets for methane emission and consumption, achieving nRMSE values as low as 0.43 and 0.88 with corresponding R2 scores up to 0.97 and 0.68 for emission prediction.

Rongchao Dong, Yiming Sun, Shuo Chen +4

University of Pittsburgh · Purdue University · University of Colorado Boulder +3

Meta-LearningSpatiotemporal Forecasting
AskPDF
May 27, 2026

You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the underlying LLMs. In this paper, we demonstrate that test-time refinement of the skill evolving framework itself is necessary for continuous improvement of the agent systems in different downstream scenarios, and lightweight algorithmic adaptation is feasible. Specifically, we propose HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from agents' task execution traces. Experiments on diverse agentic benchmarks show that meta-evolving can produce a higher-quality skill library than pure skill evolving and can derive diverse meta-skills for different scenarios, thereby facilitating future continual experience learning. Our code is temporarily public at https://anonymous.4open.science/r/HiSME-BD45.

Xujun Li, Kehan Zheng, Mingyuan Zhao +7

Department of Computer Science and Technology, Tsinghua University · Huawei Foundation Model Department

Meta-LearningLLM Agent Skill LearningSelf-Evolving Agents
AskPDF
May 23, 2026

Advancing Graph Few-Shot Learning via In-Context Learning

Graph few-shot learning, which aims to classify nodes from novel classes with only a few labeled examples, is a widely studied problem in graph learning. However, existing methods often face two key limitations. First, the predominant graph few-shot learning paradigm relies on supervised tasks, failing to leverage the vast number of unlabeled nodes in the graph. Second, many approaches require complex task adaptation or fine-tuning during inference, limiting their efficiency and applicability. Inspired by the powerful in-context learning capabilities of large language models, we propose a novel model named VISION for adVancIng graph few-Shot learning via In-cOntext LearNing to address these challenges. Our model reframes graph few-shot learning as a fine-tuning-free sequence reasoning problem. At its core is a context-aware network that initializes nodes with role embeddings and employs a dual-context fusion module to synergistically integrate local topological structures and global task-level dependencies. This allows our model to dynamically generate class-aware representations for the query set conditioned on the support set context in a single forward pass. To effectively train our model, we introduce an unsupervised task generator that creates structure-adaptive features and constructs diverse pseudo-tasks from abundant unlabeled data. Our method unifies unsupervised meta-learning with graph in-context learning, achieving efficient inference. Extensive experiments on multiple benchmark datasets demonstrate the superiority of our model. Our public code can be found

Renchu Guan, Yajun Wang, Chunli Guo +5

Key Laboratory of Symbolic Computation and Knowledge Engineering of the Ministry of Education

Meta-LearningFew-Shot LearningIn-Context Learning
AskPDF
May 21, 2026

Meta-Learning for Rapid Adaptation in Reference Tracking of Uncertain Nonlinear Systems

In this paper, we address the problem of reference tracking for uncertain nonlinear systems. Since collecting data from the target system (i.e., the system of interest) is often challenging, our objective is to design optimal controllers using limited target system data. Meta-learning provides a promising paradigm by leveraging offline data from source systems (systems sharing structural similarities with the target system) to accelerate training and enhance control performance. Motivated by this idea, we propose a meta-learning-based control framework that tailors the implicit model-agnostic meta-learning (iMAML) algorithm to the control setting. The framework operates in two phases: an (offline) meta-training phase, where an aggregated representation is learned from source data to capture the shared system dynamics among similar systems, and an (online) meta-adaptation phase, where this representation is fine-tuned on the target system using only a few data samples and limited adaptation steps. We formulate this framework as a bi-level optimization problem and provide an efficient solution with reduced storage complexity and few approximations. The proposed framework is general, allowing various learning algorithms to be integrated. To demonstrate this flexibility, we propose two specific learning algorithms that can be incorporated into our framework based on a neural state-space model and a deep Q-network, respectively. The primary distinction between these approaches is whether explicit system identification is required. Numerical simulations and hardware experiments demonstrate that the proposed methods enhance control performance and consistently outperform baseline approaches.

Jiaqi Yan, Ankush Chakrabarty, Niklas Schmid +2

School of Automation Science and Electrical Engineering, Beihang University, Beijing 100191, P. R. China · Mitsubishi Electric Research Laboratories, Cambridge, MA 02139, USA · Automatic Control Laboratory, ETH Zurich, Switzerland +1

Robot Trajectory TrackingMeta-Learning
AskPDF
May 21, 2026

ForeSplat: Optimization-Aware Foresight for Feed-Forward 3D Gaussian Splatting

Feed-forward 3D Gaussian Splatting models offer fast single-pass reconstruction,but scaling them to match per-scene optimization quality is fundamentally hindered by the scarcity of large-scale 3D annotations. A practical compromise is predict-then-refine,where post-prediction optimization compensates for the limited capacity of the feed-forward network. However,standard feed-forward 3DGS is trained solely for zero-step rendering error,ignoring whether its output constitutes a good initialization for the downstream optimizer. We present ForeSplat,an optimization-aware training framework that equips feed-forward 3DGS models to produce initializations explicitly designed for rapid,effective refinement. By offloading part of the scene-modeling burden to the optimizer,ForeSplat substantially reduces the capacity pressure on the feed-forward model,making high-quality reconstruction feasible even with compact networks. At its core is MetaGrad,a lightweight multi-anchor meta-gradient training rule that bypasses costly higher-order differentiation through the 3DGS optimizer. MetaGrad unrolls a short inner-loop refinement trajectory,samples anchor states,and back-propagates aggregated first-order gradients to the prediction head as a surrogate optimization-aware signal. This fine-tuning adds no inference cost and enables high-quality reconstruction within seconds after a few refinement steps. We instantiate ForeSplat on diverse backbones,including AnySplat,Pi3X,and a distilled variant tailored for edge deployment. Across all tested architectures,a ForeSplat-trained initialization converges in fewer refinement steps and reaches a higher peak reconstruction quality than its vanilla counterpart,even fully converged. The framework consistently bridges the gap between amortized prediction and per-scene optimization,establishing a practical path toward lightweight,high-fidelity 3D reconstruction.

Yuke Li, Weihang Liu, Cheng Zhang +8

ShanghaiTech University · GGU Technology Co., Ltd · Stereye

3D Gaussian SplattingMeta-Learning3D ReconstructionFeed-Forward 3D Reconstruction3DGS Training
AskPDF
May 20, 2026

Cumulative Meta-Learning from Active Learning Queries for Robustness to Spurious Correlations

Spurious correlations in real-world datasets cause machine learning models to rely on irrelevant patterns, undermining reliability, generalization, and fairness. Active learning offers a promising way to address this failure mode by querying informative samples that distinguish core features from spurious ones. However, standard active-learning methods simply append queried examples to the labeled set, effectively updating only the likelihood term. In deep learning regimes, the influence of these informative samples can be diluted by the larger labeled set and memorized by overparameterized models. We propose Cumulative Active Meta-Learning (CAML), an active-learning framework that uses queried examples to meta-learn the prior, or inductive bias, governing how the model adapts. CAML casts each active-learning round as a meta-learning task: the current labeled set serves as meta-train data for adaptation, while the newly queried batch serves as meta-test data for evaluating generalization. Unlike conventional meta-learning, which treats tasks as independent and identically distributed, CAML exploits the sequential dependence between active-learning rounds by maintaining a cumulative inductive bias that is progressively refined. Theoretically, we show that this cumulative formulation introduces interaction terms that couple earlier meta-learned inductive biases with later query-induced objectives, capturing dependencies absent from standard meta-learning. Empirically, CAML improves minority-group accuracy across spurious-correlation benchmarks and acquisition strategies, with gains of up to 27.8% on Dominoes, 29.9% on Waterbirds, 14.3% on SpuCo, and 24.0% on CivilComments.

Kin Whye Chew, Jingxian Wang

Department of Computer Science National University of Singapore Singapore, S119077

Meta-LearningActive LearningSpurious Correlation RobustnessSpurious Correlation
AskPDF
May 18, 2026

MANGO: Meta-Adaptive Network Gradient Optimization for Online Continual Learning

In Online Continual Learning (OCL), a neural network sequentially learns from a non-stationary data stream in a single-pass with access only to a limited memory replay buffer. This contrasts sharply with off-line continual learning where training is multiple epoch dependent on large datasets. The main challenge faced by OCL is to overcome catastrophic forgetting of past tasks (stability) while learning new ones efficiently (plasticity). Existing methods counter forgetting via replay-based rehearsal, output level distillation, fixed regularization, or meta-learning on the current data. However, these methods have limitations: rehearsal introduces a stored sample bias; distillation operates on output-distributions without modulating parameter updates; fixed-regularization penalizes parameters irrespective of sensitivity; stream-only meta-learning lacks a feedback controlled parameter update. We propose Meta-Adaptive Network Gradient Optimization (MANGO), an OCL framework that balances stability-plasticity via gradient-gating and meta-learned regularization. Gradient-gating scales parameter updates based on sensitivity, preventing destructive updates. Meta-learned regularization adapts stability coefficients, evaluating the effect of parameter update on replay. In MANGO, replay acts as both a training signal and a forgetting evaluator. We evaluated our method on three standard OCL benchmark datasets. MANGO outperforms strong baselines, achieving state-of-the-art results with consistent performance across replay sizes. In domain incremental learning on CLEAR-10 and class incremental learning on CIFAR-100 and Tiny-ImageNet, it achieves highest accuracy among all baselines and achieves positive Backward Transfer, overcoming forgetting on CLEAR-10.

Ankita Awasthi, Marco Apolinario, Kaushik Roy

Purdue University, USA · TU Delft, Netherlands

Class-Incremental LearningMeta-LearningContinual LearningReplay-Based Continual LearningOnline Continual LearningIncremental Learning+1
AskPDF
May 18, 2026

Efficient Bilevel Optimization for Meta Label Correction in Noisy Label Learning

Training a deep neural network with noisy labels could reduce data annotation cost but may introduce noise into the learned model. In meta label correction approaches, an additional meta model besides the main model is trained with a small, clean dataset to correct the large, noisy dataset. However, the update of the meta model requires the computation of hypergradients at the inner step of the main model which signif- icantly increases the computational cost. To improve the training efficiency, we first introduce the dynamic barrier gradient descent into standard meta label correction. While this naive extenstion is able to speed up the training process to approximately first- order complexity, it lacks mechanisms to prevent the leakage of noisy signals to the main model and to stabilize the learning of the meta model. Based on this observation, we propose the EBOMLC method, which is designed with three key improvements including one-step inner loop update, mixture upper loss and alignment- aware dynamic barrier. Empirical results on CIFAR-10 and CIFAR-100 demonstrate that EBOMLC consistently outperforms other baselines, especially under high noise rate settings, while reducing training time of the meta label correction approach.

Ba Hoang Anh Nguyen, Viet Cuong Ta

Human-Machine Interaction Laboratory, VNU University of Engineering and Technology, Hanoi, Vietnam

Meta-LearningNoisy-Label LearningBilevel Optimization
AskPDF
May 15, 2026

Boundedly Rational Meta-Learning in Sequential Consumer Choice

Many consumer decisions are repeated choices under uncertainty. Standard models capture these decisions using Bayesian learning and dynamic programming: consumers update beliefs from feedback and use those beliefs to guide future choices. In many markets, however, learning does not restart when consumers enter a new context: prior experience with a brand, product, or provider can shape beliefs in later, related decisions. We study this cross-context knowledge transfer, or meta-learning, in sequential choice. We design a hierarchical laboratory task in which participants repeatedly choose among airlines across routes and observe noisy binary outcomes. Reduced-form evidence shows that participants improve not only within routes, but also across routes: they choose better airlines earlier in later routes and reduce pseudo-regret. To identify the mechanism behind this transfer, we compare human choices to a no-transfer benchmark and a fully integrated Bayesian meta-learning benchmark. In particular, we introduce a class of boundedly rational meta dynamic programming policies, BRMDP(D), that approximate full integration using a limited number of hyper-posterior draws, denoted by D. Trial-by-trial likelihood comparisons show that low-D boundedly rational meta-learning, especially BRMDP(1), fits participant behavior better than both no transfer and fully integrated Bayesian transfer. Consumers, therefore, transfer brand-level regularities across contexts, but through coarse representations of prior uncertainty. The findings imply that models of consumer learning should allow for approximate cross-context transfer, and that managerial counterfactuals based on either no-transfer or fully integrated learning can be misleading.

Mehrzad Khosravi, Max Kleiman-Weiner, Hema Yoganarasimhan

University of Washington

Meta-LearningSequential Decision MakingDiscrete Choice ModelingBayesian Decision TheoryBounded RationalityDecision-Making under Uncertainty
AskPDF
May 15, 2026

EUPHORIA: Efficient Universal Planning via Hybrid Optimization for Robust Industrial Robotic Assembly

Robotic assembly in architectural construction faces a persistent bottleneck: existing planners are either highly specialized, requiring prohibitive retraining for every new geometric design, or operationally inefficient, treating structural sequencing and kinematic motion as disjoint processes. We present EUPHORIA, a unified framework that achieves universal few-shot adaptability and dynamic efficiency through a hybrid optimization strategy. To overcome the retraining bottleneck, we propose a Meta-Geometric Encoder based on Graph Hypernetworks: unlike standard contrastive learning, which performs only feature-level recognition, our hypernetwork dynamically generates policy parameters from a minimal support set, enabling parameter-level adaptation to complex topologies (e.g., domes, arches) without gradient-based retraining. For structural reasoning, we introduce a Physics-Informed Graph Transformer trained via Soft Actor-Critic (SAC), with a Physics-Bias Attention mechanism that modulates attention scores using contact forces from Discrete Element Model (DEM) simulations, guiding the planner toward structurally critical connections. We further ensure operational efficiency through Kinematics-Aware Sequencing, where the SAC objective penalizes high-energy transitions. Finally, we bridge the Sim2Real gap via Residual Stability Correction, a differentiable optimization layer that fine-tunes coarse assembly actions by minimizing a joint energy-stability cost prior to execution. Experiments show that EUPHORIA significantly reduces energy consumption over decoupled baselines and achieves state-of-the-art success rates on unseen, non-standard geometries with minimal few-shot examples, fusing meta-learning, physics-informed attention, and residual optimization into a cohesive, generalized planner.

Shih-Yu Lai, Chia-Ching Yen, Yang-Ting Shen +3

National Taiwan University · MoonShine Animation Studio · National Cheng Kung University +2

Robotic ConstructionMeta-LearningRobotic RLRobot Task PlanningGraph-Based PlanningIndustrial Robotics+2
AskPDF
May 15, 2026

Seeking the Unfamiliar but Memorable: Conceptual Creativity as Meta-Learning

What does it mean to create a new concept, rather than retrieve a familiar one? Repeatedly sampling a generative model at the same prompt produces variations with similar styles and typical content. We propose that creativity is the production of stimuli that are unfamiliar to an adaptive observer at first sight, but quickly learnable from a few exposures. We formalize this as a Creator-Appraiser pair: a Creator generates a candidate, an Appraiser adapts to it for a few inner-loop learning steps, and the Appraiser's improvement becomes the reward the Creator optimizes through. We instantiate the framework with diffusion as the Creator, an autoencoder Appraiser on MNIST, and a CLIP Appraiser with a low-rank adapter for natural images. The diffusion model remains frozen with no additional language conditioning; the meta-learning gradient is enough to produce both stylistic variations and concept compositions that the base model does not generate on its own.

Mengye Ren

Agentic Learning AI Lab, New York University

Meta-LearningComputational Creativity
AskPDF
May 15, 2026

Learn2Splat: Extending the Horizon of Learned 3DGS Optimization

3D Gaussian Splatting (3DGS) optimization is most commonly performed using general-purpose first-order optimizers such as Adam or SGD. Although robust across scenes, they update each parameter independently without exploiting the structural and spatial relationships among Gaussians, which slows convergence. Recent works introduced learned optimizers that predict correlated updates informed by inter-parameter and inter-Gaussian dependencies. However, those are trained for a fixed number of optimization iterations and rely on manually scheduled learning rates to avoid degradation. In this paper, we introduce Learn2Splat, a learned optimizer for 3DGS that avoids degradation over extended optimization horizons without auxiliary mechanisms. To enable this, we propose a meta-learning scheme that extends the optimization horizon via a checkpoint buffer and an optimizer rollout strategy, combined with an architecture that encodes gradient scale information in its latent states. Results show higher novel view synthesis quality at equal wall-clock time, while remaining stable over long horizons, with zero-shot generalization to unseen datasets and settings. To support our findings, we build a unified framework to train and evaluate learned and standard optimizers across sparse and dense view settings. Code and models will be released publicly. Our project page is available at https://autonomousvision.github.io/learn2splat .

Naama Pearl, Stefano Esposito, Haofei Xu +6

University of Tübingen, Tübingen AI Center · ETH Zurich · Meta Reality Labs

3D Gaussian SplattingMeta-LearningLearning to OptimizeNovel View Synthesis3DGS Training
AskPDF